Author :
Garland, Michael ; Grand, Scott Le ; Nickolls, John ; Anderson, Joshua ; Hardwick, Jim ; Morton, Scott ; Phillips, Everett ; Zhang, Yao ; Volkov, Vasily
Abstract :
The CUDA programming model provides a straightforward means of describing inherently parallel computations, and NVIDIA´s Tesla GPU architecture delivers high computational throughput on massively parallel problems. This article surveys experiences gained in applying CUDA to a diverse set of problems and the parallel speedups over sequential codes running on traditional CPU architectures attained by executing key computations on the GPU.
Keywords :
coprocessors; parallel processing; CUDA programming model; NVIDIA; Tesla GPU architecture; parallel computing; sequential codes; Central Processing Unit; Computer architecture; Computer graphics; Concurrent computing; Kernel; Parallel processing; Parallel programming; Programming profession; Throughput; Yarn;
